• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.239-251
• /
• 2019

Statistical methods such as moving averages, Kalman filtering, exponential smoothing, regression analysis, and ARIMA (autoregressive integrated moving average) have been used for stock market predictions. However, these statistical methods have not produced superior performances. In recent years, machine learning techniques have been widely used in stock market predictions, including artificial neural network, SVM, and genetic algorithm. In particular, a case-based reasoning method, known as k-nearest neighbor is also widely used for stock price prediction. Case based reasoning retrieves several similar cases from previous cases when a new problem occurs, and combines the class labels of similar cases to create a classification for the new problem. However, case based reasoning has some problems. First, case based reasoning has a tendency to search for a fixed number of neighbors in the observation space and always selects the same number of neighbors rather than the best similar neighbors for the target case. So, case based reasoning may have to take into account more cases even when there are fewer cases applicable depending on the subject. Second, case based reasoning may select neighbors that are far away from the target case. Thus, case based reasoning does not guarantee an optimal pseudo-neighborhood for various target cases, and the predictability can be degraded due to a deviation from the desired similar neighbor. This paper examines how the size of learning data affects stock price predictability through k-nearest neighbor and compares the predictability of k-nearest neighbor with the random walk model according to the size of the learning data and the number of neighbors. In this study, Samsung electronics stock prices were predicted by dividing the learning dataset into two types. For the prediction of next day's closing price, we used four variables: opening value, daily high, daily low, and daily close. In the first experiment, data from January 1, 2000 to December 31, 2017 were used for the learning process. In the second experiment, data from January 1, 2015 to December 31, 2017 were used for the learning process. The test data is from January 1, 2018 to August 31, 2018 for both experiments. We compared the performance of k-NN with the random walk model using the two learning dataset. The mean absolute percentage error (MAPE) was 1.3497 for the random walk model and 1.3570 for the k-NN for the first experiment when the learning data was small. However, the mean absolute percentage error (MAPE) for the random walk model was 1.3497 and the k-NN was 1.2928 for the second experiment when the learning data was large. These results show that the prediction power when more learning data are used is higher than when less learning data are used. Also, this paper shows that k-NN generally produces a better predictive power than random walk model for larger learning datasets and does not when the learning dataset is relatively small. Future studies need to consider macroeconomic variables related to stock price forecasting including opening price, low price, high price, and closing price. Also, to produce better results, it is recommended that the k-nearest neighbor needs to find nearest neighbors using the second step filtering method considering fundamental economic variables as well as a sufficient amount of learning data.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.49 no.4
• /
• pp.15-29
• /
• 2021

The study aims to grasp the perception and appraisal of urban park users through text analysis. This study used Google review data provided by Google Maps. Google Maps Review is an online review platform that provides information evaluating locations through social media and provides an understanding of locations from the perspective of general reviewers and regional guides who are registered as members of Google Maps. The study determined if the Google Maps Reviews were useful for extracting meaningful information about the user perceptions and appraisals for parks management plans. The study chose three urban parks in Seoul, South Korea; Seoul Forest, Boramae Park, and Olympic Park. Review data for each of these three parks were collected via web crawling using Python. Through text analysis, the keywords and network structure characteristics for each park were analyzed. The text was analyzed, as were park ratings, and the analysis compared the reviews of residents and foreign tourists. The common keywords found in the review comments for the three parks were "walking", "bicycle", "rest" and "picnic" for activities, "family", "child" and "dogs" for accompanying types, and "playground" and "walking trail" for park facilities. Looking at the characteristics of each park, Seoul Forest shows many outdoor activities based on nature, while the lack of parking spaces and congestion on weekends negatively impacted users. Boramae Park has the appearance of a city park, with various facilities providing numerous activities, but reviewers often cited the park's complexity and the negative aspects in terms of dog walking groups. At Olympic Park, large-scale complex facilities and cultural events were frequently mentioned, emphasizing its entertainment functions. Google Maps Review can function as useful data to identify parks' overall users' experiences and general feelings. Compared to data from other social media sites, Google Maps Review's data provides ratings and understanding factors, including user satisfaction and dissatisfaction.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.111-136
• /
• 2018

In this paper, we propose a methodology to extract answer information about queries from various types of unstructured documents collected from multi-sources existing on web in order to expand knowledge base. The proposed methodology is divided into the following steps. 1) Collect relevant documents from Wikipedia, Naver encyclopedia, and Naver news sources for "subject-predicate" separated queries and classify the proper documents. 2) Determine whether the sentence is suitable for extracting information and derive the confidence. 3) Based on the predicate feature, extract the information in the proper sentence and derive the overall confidence of the information extraction result. In order to evaluate the performance of the information extraction system, we selected 400 queries from the artificial intelligence speaker of SK-Telecom. Compared with the baseline model, it is confirmed that it shows higher performance index than the existing model. The contribution of this study is that we develop a sequence tagging model based on bi-directional LSTM-CRF using the predicate feature of the query, with this we developed a robust model that can maintain high recall performance even in various types of unstructured documents collected from multiple sources. The problem of information extraction for knowledge base extension should take into account heterogeneous characteristics of source-specific document types. The proposed methodology proved to extract information effectively from various types of unstructured documents compared to the baseline model. There is a limitation in previous research that the performance is poor when extracting information about the document type that is different from the training data. In addition, this study can prevent unnecessary information extraction attempts from the documents that do not include the answer information through the process for predicting the suitability of information extraction of documents and sentences before the information extraction step. It is meaningful that we provided a method that precision performance can be maintained even in actual web environment. The information extraction problem for the knowledge base expansion has the characteristic that it can not guarantee whether the document includes the correct answer because it is aimed at the unstructured document existing in the real web. When the question answering is performed on a real web, previous machine reading comprehension studies has a limitation that it shows a low level of precision because it frequently attempts to extract an answer even in a document in which there is no correct answer. The policy that predicts the suitability of document and sentence information extraction is meaningful in that it contributes to maintaining the performance of information extraction even in real web environment. The limitations of this study and future research directions are as follows. First, it is a problem related to data preprocessing. In this study, the unit of knowledge extraction is classified through the morphological analysis based on the open source Konlpy python package, and the information extraction result can be improperly performed because morphological analysis is not performed properly. To enhance the performance of information extraction results, it is necessary to develop an advanced morpheme analyzer. Second, it is a problem of entity ambiguity. The information extraction system of this study can not distinguish the same name that has different intention. If several people with the same name appear in the news, the system may not extract information about the intended query. In future research, it is necessary to take measures to identify the person with the same name. Third, it is a problem of evaluation query data. In this study, we selected 400 of user queries collected from SK Telecom 's interactive artificial intelligent speaker to evaluate the performance of the information extraction system. n this study, we developed evaluation data set using 800 documents (400 questions * 7 articles per question (1 Wikipedia, 3 Naver encyclopedia, 3 Naver news) by judging whether a correct answer is included or not. To ensure the external validity of the study, it is desirable to use more queries to determine the performance of the system. This is a costly activity that must be done manually. Future research needs to evaluate the system for more queries. It is also necessary to develop a Korean benchmark data set of information extraction system for queries from multi-source web documents to build an environment that can evaluate the results more objectively.

• Journal of Intelligence and Information Systems
• /
• v.26 no.3
• /
• pp.91-108
• /
• 2020

Korea's famous soccer players are steadily performing well in international leagues, which led to higher interests of Korean fans in the international leagues. Reflecting the growing social phenomenon of rising interests on international leagues by Korean fans, the study examined the overall consumer perception in the consumption of uniform by domestic soccer fans and compared the changes in perception following the transfers of the players. Among others, the paper examined the consumer perception and purchase factors of soccer fans shown in social media, focusing on periods before and after the recruitment of Heung-Min Son to English Premier League's Tottenham Football Club. To this end, the EPL uniform is the collection keyword the paper utilized and collected consumer postings from domestic website and social media via Python 3.7, and analyzed them using Ucinet 6, NodeXL 1.0.1, and SPSS 25.0 programs. The results of this study can be summarized as follows. First, the uniform of the club that consistently topped the league, has been gaining attention as a popular uniform, and the players' performance, and the players' position have been identified as key factors in the purchase and search of professional football uniforms. In the case of the club, the actual ranking and whether the league won are shown to be important factors in the purchase and search of professional soccer uniforms. The club's emblem and the sponsor logo that will be attached to the uniform are also factors of interest to consumers. In addition, in the decision making process of purchase of a uniform by professional soccer fan, uniform's form, marking, authenticity, and sponsors are found to be more important than price, design, size, and logo. The official online store has emerged as a major purchasing channel, followed by gifts for friends or requests from acquaintances when someone travels to the United Kingdom. Second, a classification of key control categories through the convergence of iteration correlation analysis and Clauset-Newman-Moore clustering algorithm shows differences in the classification of individual groups, but groups that include the EPL's club and player keywords are identified as the key topics in relation to professional football uniforms. Third, between 2002 and 2006, the central theme for professional football uniforms was World Cup and English Premier League, but from 2012 to 2015, the focus has shifted to more interest of domestic and international players in the English Premier League. The subject has changed to the uniform itself from this time on. In this context, the paper can confirm that the major issues regarding the uniforms of professional soccer players have changed since Ji-Sung Park's transfer to Manchester United, and Sung-Yong Ki, Chung-Yong Lee, and Heung-Min Son's good performances in these leagues. The paper also identified that the uniforms of the clubs to which the players have transferred to are of interest. Fourth, both male and female consumers are showing increasing interest in Son's league, the English Premier League, which Tottenham FC belongs to. In particular, the increasing interest in Son has shown a tendency to increase interest in football uniforms for female consumers. This study presents a variety of researches on sports consumption and has value as a consumer study by identifying unique consumption patterns. It is meaningful in that the accuracy of the interpretation has been enhanced by using a cluster analysis via convergence of iteration correlation analysis and Clauset-Newman-Moore clustering algorithm to identify the main topics. Based on the results of this study, the clubs will be able to maximize its profits and maintain good relationships with fans by identifying key drivers of consumer awareness and purchasing for professional soccer fans and establishing an effective marketing strategy.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.139-156
• /
• 2021

The biggest reason for using a deep learning model in image classification is that it is possible to consider the relationship between each region by extracting each region's features from the overall information of the image. However, the CNN model may not be suitable for emotional image data without the image's regional features. To solve the difficulty of classifying emotion images, many researchers each year propose a CNN-based architecture suitable for emotion images. Studies on the relationship between color and human emotion were also conducted, and results were derived that different emotions are induced according to color. In studies using deep learning, there have been studies that apply color information to image subtraction classification. The case where the image's color information is additionally used than the case where the classification model is trained with only the image improves the accuracy of classifying image emotions. This study proposes two ways to increase the accuracy by incorporating the result value after the model classifies an image's emotion. Both methods improve accuracy by modifying the result value based on statistics using the color of the picture. When performing the test by finding the two-color combinations most distributed for all training data, the two-color combinations most distributed for each test data image were found. The result values were corrected according to the color combination distribution. This method weights the result value obtained after the model classifies an image's emotion by creating an expression based on the log function and the exponential function. Emotion6, classified into six emotions, and Artphoto classified into eight categories were used for the image data. Densenet169, Mnasnet, Resnet101, Resnet152, and Vgg19 architectures were used for the CNN model, and the performance evaluation was compared before and after applying the two-stage learning to the CNN model. Inspired by color psychology, which deals with the relationship between colors and emotions, when creating a model that classifies an image's sentiment, we studied how to improve accuracy by modifying the result values based on color. Sixteen colors were used: red, orange, yellow, green, blue, indigo, purple, turquoise, pink, magenta, brown, gray, silver, gold, white, and black. It has meaning. Using Scikit-learn's Clustering, the seven colors that are primarily distributed in the image are checked. Then, the RGB coordinate values of the colors from the image are compared with the RGB coordinate values of the 16 colors presented in the above data. That is, it was converted to the closest color. Suppose three or more color combinations are selected. In that case, too many color combinations occur, resulting in a problem in which the distribution is scattered, so a situation fewer influences the result value. Therefore, to solve this problem, two-color combinations were found and weighted to the model. Before training, the most distributed color combinations were found for all training data images. The distribution of color combinations for each class was stored in a Python dictionary format to be used during testing. During the test, the two-color combinations that are most distributed for each test data image are found. After that, we checked how the color combinations were distributed in the training data and corrected the result. We devised several equations to weight the result value from the model based on the extracted color as described above. The data set was randomly divided by 80:20, and the model was verified using 20% of the data as a test set. After splitting the remaining 80% of the data into five divisions to perform 5-fold cross-validation, the model was trained five times using different verification datasets. Finally, the performance was checked using the test dataset that was previously separated. Adam was used as the activation function, and the learning rate was set to 0.01. The training was performed as much as 20 epochs, and if the validation loss value did not decrease during five epochs of learning, the experiment was stopped. Early tapping was set to load the model with the best validation loss value. The classification accuracy was better when the extracted information using color properties was used together than the case using only the CNN architecture.